Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ProgressBar
    -0.08
    	rect
    -0.07
     Plasma
    -0.07
    sector
    -0.07
     Folder
    -0.06
    .smart
    -0.06
    Size
    -0.06
     तस
    -0.06
     sais
    -0.06
    umin
    -0.06
    POSITIVE LOGITS
    ρος
    0.06
    нее
    0.06
     دقی
    0.06
     shy
    0.06
    ệ
    0.06
    ΟΜ
    0.06
    เน
    0.06
    avian
    0.06
     educated
    0.06
    .!
    0.06
    Act Density 0.024%

    No Known Activations